Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

Investigating techniques for low resource conversational speech recognition

Abstract : In this paper we investigate various techniques in order to build effective speech to text (STT) and keyword search (KWS) systems for low resource conversational speech. Sub-word decoding and graphemic mappings were assessed in order to detect out-of-vocabulary keywords. To deal with the limited amount of transcribed data, semi-supervised training and data selection methods were investigated. Robust acoustic features produced via data augmentation were evaluated for acoustic modeling. For language modeling, automatically retrieved conversational-like Webdata was used, as well as neural network based models. We report STT improvements with all the techniques, but interestingly only some improve KWS performance. Results are reported for the Swahili language in the context of the 2015 OpenKWS Evaluation.
Type de document :
Communication dans un congrès
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal-univ-lemans.archives-ouvertes.fr/hal-01515254
Contributeur : Antoine Laurent <>
Soumis le : jeudi 27 avril 2017 - 10:48:39
Dernière modification le : mercredi 16 septembre 2020 - 17:26:21
Archivage à long terme le : : vendredi 28 juillet 2017 - 12:30:55

Fichier

Laurent16.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Antoine Laurent, Thiago Fraga-Silva, Lori Lamel, Jean-Luc Gauvain. Investigating techniques for low resource conversational speech recognition. 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), Mar 2016, Shangai, China. pp.5975-5979, ⟨10.1109/ICASSP.2016.7472824⟩. ⟨hal-01515254⟩

Partager

Métriques

Consultations de la notice

192

Téléchargements de fichiers

108